Large language models in global health - Nature Health Large language models (LLMs) are emerging as powerful tools in healthcare, with a growing role in global health, particularly in low- and middle-income countries. This Perspective examines the current...

GenAI has the potential to worsen health inequities. In a new review we show that with intent, confronting the challenges, it could be just the opposite, globally
led by @nliulab.bsky.social
nature.com/articles/s44...

Equitable impact of an AI-driven breast cancer screening workflow in real-world US-wide deployment - Nature Health In a prospective study involving 579,583 women in multiple sites across the USA, a multistage AI-driven workflow for digital breast tomosynthesis mammograms assisted radiologists in identifying 21.6% ...

In a prospective study involving 208,891 women in multiple sites across the US, an AI-based system assisted radiologists in identifying 21.6% more cancers with respect to historical data, showing no significant variation across socio-demographic subgroups.

www.nature.com/articles/s44...

Equitable impact of an AI-driven breast cancer screening workflow in real-world US-wide deployment - Nature Health In a prospective study involving 579,583 women in multiple sites across the USA, a multistage AI-driven workflow for digital breast tomosynthesis mammograms assisted radiologists in identifying 21.6% ...

The first ever paper in Nature Health!

In a prospective study involving 208,891 women in multiple sites across the US, a digital breast tomosynthesis-adapted algorithm assisted radiologists in identifying 21.6% more cancers with respect to historical data

www.nature.com/articles/s44...

Clinical implementation of an AI-based prediction model for decision support for patients undergoing colorectal cancer surgery - Nature Medicine A model developed with data from 19,403 patients with colorectal cancer for prediction of 1-year mortality is used as a decision support tool in a prospective cohort, showing promising results in redu...

A model developed with data from 19,403 patients with colorectal cancer for prediction of one-year mortality is used as a decision support tool in a prospective cohort, showing promising results in reducing post-operative complications

www.nature.com/articles/s41...

It is one of my favourite conferences, so I could not miss it! I will be attending #Epidemics10 this year in San Diego for Nature Health - please let me know if you are attending and would like to meet at the conference to chat!

Influenza vaccine strain selection with an AI-based evolutionary and antigenicity model - Nature Medicine By matching antigenicity prediction with a forecast of circulating strains in the next season, a model is shown to outperform standard recommendations for vaccine design in terms of vaccine effectiven...

By matching antigenicity prediction with a forecast of circulating strains in the next season, a model is shown to outperform standard recommendations for vaccine design in terms of vaccine effectiveness and disease burden
www.nature.com/articles/s41...

Training and validated on multimodal data from 14.5 million images from multi-country datasets, a foundation model is shown to increase diagnostic and referral accuracy of clinicians when used as an assistant in a trial involving 16 ophthalmologists and 668 patients

www.nature.com/articles/s41...

AI-based diagnosis of acute aortic syndrome from noncontrast CT - Nature Medicine Going from model development to a pilot implementation study, a deep learning model shows that acute aortic syndrome can be diagnosed directly from noncontrast CT, increasing accuracy and decreasing t...

Going from model development to a pilot implementation study, a deep learning model shows acute aortic syndrome can be diagnosed directly from non-contrast CT, increasing accuracy and decreasing time to diagnosis

www.nature.com/articles/s41...

Using large cohorts from published clinical trials involving more than 8,000 patients, a probabilistic machine learning model shows patterns that suggest how progression to severe stages occur and potential inversion of the process

www.nature.com/articles/s41...

Countrywide natural experiment links built environment to physical activity - Nature By analysing the smartphone data of 2,112,288 participants, in particular observing and comparing the activity of the same individual in two different environments, we find that increases in the walkability of environments result in increases in daily physical activity, providing evidence of the importance of the built environment on physical health.

Nature research paper: Countrywide natural experiment links built environment to physical activity

go.nature.com/46W2lFl

AI-driven multi-omics modeling of myalgic encephalomyelitis/chronic fatigue syndrome - Nature Medicine Analysis of a deeply phenotyped, longitudinal cohort of 249 participants elucidates the network of concurrent molecular and macroscopic patterns related to insurgence and course of ME/CFS.

Analysis of a deeply phenotyped, longitudinal cohort of 249 participants elucidates the network of concurrent molecular and macroscopic patterns related to insurgence and course of ME/CFS

www.nature.com/articles/s41...

AI-driven multi-omics modeling of myalgic encephalomyelitis/chronic fatigue syndrome - Nature Medicine Analysis of a deeply phenotyped, longitudinal cohort of 249 participants elucidates the network of concurrent molecular and macroscopic patterns related to insurgence and course of ME/CFS.

Multi-omics with A.I. analytics demonstrates critical role of the gut microbiome and immune response and enables accurate diagnosis of ME/CFS, may also be applicable to Long Covid.
www.nature.com/articles/s41...
www.ft.com/content/9cdf...

Agentic A.I. to predict body-wide and organ specific biological aging with associated health outcomes
www.nature.com/articles/s41...

Large language model-based biological age prediction in large-scale populations - Nature Medicine Using data from six population-scale cohorts involving more than 10 million individuals, a large language model-based aging signature is shown to outperform traditional aging biomarker indices and sig...

Using data from six population-scale cohorts involving more than ten million individuals, a large language model-based aging signature is shown to outperform traditional aging biomarker indices and signatures in predicting multiple health outcomes

www.nature.com/articles/s41...

Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection - Nature Medicine In a silent trial involving 197 patients with lung cancer over a span of 4 months, a fine-tuned pathology foundation model was able to identify the presence of EGFR mutations with high accuracy, poten...

In a silent trial involving 197 lung cancer patients over the span of four months, a pathology foundation model was able to identify presence of EGFR mutations with high accuracy, potentially preventing further genetic testing in 43% of cases

www.nature.com/articles/s41...

Efficacy, public health impact and optimal use of the Takeda dengue vaccine - Nature Medicine Using mathematical models calibrated to clinical trial results on vaccine efficacy, this study projects the potential impact of the vaccine at population level, showing the conditions for it to be eff...

Using mathematical models calibrated to clinical trial results on vaccine efficacy, this study projects the potential impact of the vaccine at population level, helping to design vaccination campaigns @imperialcollegeldn.bsky.social

www.nature.com/articles/s41...

An adaptive AI-based virtual reality sports system for adolescents with excess body weight: a randomized controlled trial - Nature Medicine A reinforcement learning-based virtual reality system, implementing a series of sport sessions with coaching, was as effective as standard physical activity in reducing fat mass in adolescents, with p...

A reinforcement learning-based virtual reality system, implementing a series of sport sessions with coaching, was as effective as standard physical activity in reducing fat mass in adolescents, with positive effects on cognition.

www.nature.com/articles/s41...

Incorporating genetic data improves target trial emulations and informs the use of polygenic scores in randomized controlled trial design Nature Genetics - This study integrates polygenic risk scores with four emulated clinical trials using FinnGen data and shows the feasibility of this approach while highlighting potential pitfalls.

Can we use genetics to make real-world evidence more like randomized trials and improve trial design in the process?

In our latest paper, we emulate 4 cardiometabolic RCTs in
FinnGen and test how polygenic scores can improve trial emulation

rdcu.be/eryti

Applications close this Friday, 20th June.

A multimodal vision foundation model for clinical dermatology - Nature Medicine Trained on large and multicenter datasets with different imaging modalities, a foundation model is shown to have strong performance on the full spectrum of clinically relevant tasks and to increase us...

Trained on large and multicenter datasets with different imaging modalities, a foundation model is shown to have strong performance on the full spectrum of clinically relevant tasks and to increase user accuracy in diagnostic tasks

www.nature.com/articles/s41...

Thanks Adam!

Starting this week I am formally employed as Senior Editor for Nature Health, a new journal dedicated to population health and all aspects of real word implementation of health preservation policies - feel free to reach out if you have questions about the journal!

The first generative AI drug to get to a Phase 2 randomized clinical trial. The small molecule in pill form, rentosertib, showed signs of efficacy for idiopathic pulmonary fibrosis @naturemedicine.bsky.social
www.nature.com/articles/s41...

Associate or Senior Editor, Nature Medicine, Digital Medicine and Artificial Intelligence  Job Title: Associate or a Senior, Nature Medicine (Digital Medicine and Artificial Intelligence) Location: New York or Milan (Hybrid Working) Application Deadline: May 30, 2025 About Springer Nature G...

📣 #NatureMedicine is hiring a new editor with expertise in #AI, #DigitalMedicine and/or Health #Informatics! This job is open to applicants in NYC 🗽and Milano 🎭! Deadline is Fri, May 30th. Please share!
springernature.wd3.myworkdayjobs.com/SpringerNatu...

cc: @natureportfolio.nature.com

On the conversational persuasiveness of GPT-4 - Nature Human Behaviour Salvi et al. find that GPT-4 outperforms humans in debates when given basic sociodemographic data. With personalization, GPT-4 had 81.2% higher odds of post-debate agreement than humans.

This new paper finds that GPT-4 outperforms humans in debates when prompted with basic sociodemographic data.
@frasalvi.bsky.social @manoelhortaribeiro.bsky.social @ricgallotti.bsky.social
www.nature.com/articles/s41...

Associate or Senior Editor, Nature Medicine, Digital Medicine and Artificial Intelligence  Job Title: Associate or a Senior, Nature Medicine (Digital Medicine and Artificial Intelligence) Location: New York or Milan (Hybrid Working) Application Deadline: May 30, 2025 About Springer Nature G...

I will soon be transitioning to a new position, so Nature Medicine is now looking for a new medical AI editor! Please let me know if you have any questions about what the position entails. Feel free to disseminate!

springernature.wd3.myworkdayjobs.com/SpringerNatu...

Sociodemographic biases in medical decision making by large language models - Nature Medicine A panel of nine LLMs was exposed to simulated clinical cases with switched sociodemographic features exploring ethnic, social, sexual orientation and gender dimensions and showed differences in recomm...

A panel of 9 LLMs was exposed to simulated clinical cases with switched sociodemographic features exploring various dimensions and showed differences in recommendations for patient treatment, referral and follow-up @girishnadkarni.bsky.social

www.nature.com/articles/s41...

Two early studies reveal capabilities and shortcomings of Deepseek in clinical uses, with evaluation on pre-existing benchmark data

www.nature.com/articles/s41...
www.nature.com/articles/s41...

Clinical implementation of AI-based screening for risk for opioid use disorder in hospitalized adults - Nature Medicine In a quasi-experimental, pre–post-implementation study involving 51,760 hospitalizations, an electronic health record-based risk prediction model informed clinicians of patients needing consultation o...

In an implementation study involving 51,760 hospitalizations, an EHR-based risk prediction model informed clinicians of patients needing consultation on Opioid Use Disorder and decreased readmissions to the hospital @majeans2011.bsky.social

www.nature.com/articles/s41...

Real-time surveillance system for patient deterioration: a pragmatic cluster-randomized controlled trial - Nature Medicine In a large pragmatic cluster-randomized trial involving 74 clinical units in 2 health systems in the United States, a real-time alert system assisting clinical care teams in identifying patients at ri...

In a large pragmatic cluster-randomized trial involving 74 sites in 2 health systems in the US, a real-time alert system assisting nurses in identifying patients at risk of deterioration decreased mortality risk by 35.6%, with positive effects also on length of stay

www.nature.com/articles/s41...